CN112187870B - Bandwidth smoothing method and device - Google Patents
Bandwidth smoothing method and device Download PDFInfo
- Publication number
- CN112187870B CN112187870B CN202010921218.6A CN202010921218A CN112187870B CN 112187870 B CN112187870 B CN 112187870B CN 202010921218 A CN202010921218 A CN 202010921218A CN 112187870 B CN112187870 B CN 112187870B
- Authority
- CN
- China
- Prior art keywords
- bandwidth
- moment
- value
- time window
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/50—Queue scheduling
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Algebra (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The embodiment of the application provides a bandwidth smoothing method and a bandwidth smoothing device, which relate to the technical field of computers, and the method specifically comprises the following steps: the method comprises the steps of firstly determining the bandwidth fluctuation gain of a first moment according to bandwidth data in a first time window, and then determining the bandwidth fluctuation value of the first moment according to the bandwidth fluctuation gain of the first moment and the bandwidth fluctuation value of a second moment, wherein the second moment is a moment before the first moment. And when the bandwidth fluctuation value at the first moment is larger than a preset threshold value, smoothing the bandwidth data at the first moment, and sending the smoothed bandwidth data at the first moment to the scheduling system, otherwise, sending the bandwidth data at the first moment to the scheduling system. When the bandwidth fluctuation value is larger than the preset threshold value, the bandwidth data is subjected to smoothing processing instead of smoothing processing on the bandwidth data at each moment, so that bandwidth delay caused by global smoothing is avoided, the smooth bandwidth data can be sent to a scheduling system, and the accuracy of resource scheduling is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of computers, in particular to a bandwidth smoothing method and device.
Background
A CDN (Content Delivery Network) is a Network that allows a user to obtain needed Content nearby by setting up a node or a server between a service provider and a consumer, so as to achieve the purposes of alleviating Network congestion and increasing the response speed of the user in accessing a website. In the CDN network service process, the scheduling system needs to determine whether to introduce the bandwidth of another node/node group or overload the bandwidth of the node/node group according to the real-time bandwidth condition of the node/node group, so as to accurately control the load condition of the node/node group and achieve the purpose of guaranteeing high-quality service. However, due to the fluctuation of the machine load under the node/node group or the transmission network itself, the bandwidth data collected from the node/node group is not stable, and therefore the scheduling system needs to smooth the bandwidth before use.
At present, no matter whether the bandwidth of a node/group is stable or not, smoothing is uniformly performed, so that great delay is easily caused, and a scheduling system can obtain an approximate bandwidth after delaying for several minutes.
Disclosure of Invention
The embodiment of the application provides a bandwidth smoothing method and device aiming at the problem of bandwidth delay caused by global smoothing.
In one aspect, an embodiment of the present application provides a bandwidth smoothing method, including:
acquiring bandwidth data of resource equipment in a first time window, wherein the first time window is a time period determined based on a first moment;
determining the bandwidth fluctuation gain of the first moment according to the bandwidth data in the first time window;
determining a bandwidth fluctuation value of the first moment according to the bandwidth fluctuation gain of the first moment and a bandwidth fluctuation value of a second moment, wherein the second moment is a moment before the first moment;
and when the bandwidth fluctuation value at the first moment is determined to be larger than a preset threshold value, smoothing the bandwidth data of the resource equipment at the first moment, and sending the smoothed bandwidth data at the first moment to a scheduling system.
Because the mobility detection is performed on the bandwidth data at the first moment, when the bandwidth fluctuation value at the first moment is determined to be greater than the preset threshold value, the bandwidth data at the first moment is subjected to smoothing processing instead of smoothing processing on the bandwidth data at each moment, so that bandwidth delay caused by global smoothing is avoided.
Optionally, the determining, according to the bandwidth data in the first time window, the bandwidth fluctuation gain at the first time includes:
determining a bandwidth peak value in the first time window and a bandwidth differential value in the first time window according to the bandwidth data in the first time window;
determining the bandwidth fluctuation rate of the first moment according to the bandwidth peak value in the first time window and the bandwidth difference value in the first time window;
and determining the bandwidth fluctuation gain of the first moment according to the bandwidth fluctuation rate of the first moment.
The bandwidth peak value and the bandwidth difference value are adopted to determine the bandwidth fluctuation rate, and then the bandwidth fluctuation gain is determined based on the bandwidth fluctuation rate, so that the bandwidth peak value and the bandwidth fluctuation are considered, the fluctuation condition of the node/group bandwidth under the normal condition can be identified, the sudden increase/sudden decrease condition concerned by a scheduling system can be judged, and the problem of misadjustment or misadjustment caused by the loss of sudden increase/sudden decrease information is avoided.
Optionally, the bandwidth data in the first time window includes bandwidth values acquired at each acquisition time in the first time window;
determining a bandwidth peak value in the first time window and a bandwidth differential value in the first time window according to the bandwidth data in the first time window, including:
taking the maximum bandwidth value as a bandwidth peak value in the bandwidth values acquired at each acquisition time in the first time window;
and determining a first-order difference value of bandwidth values of adjacent acquisition moments in the first time window.
Optionally, the determining, according to the bandwidth peak value in the first time window and the bandwidth differential value in the first time window, the bandwidth fluctuation rate at the first time includes:
dividing the bandwidth difference value within the first time window into a positive bandwidth difference value and a negative bandwidth difference value;
determining a maximum positive bandwidth difference value from each positive bandwidth difference value;
determining the maximum negative bandwidth difference value from each negative bandwidth difference value after taking the absolute value of each negative bandwidth difference value;
summing the bandwidth difference values in the first time window to obtain a bandwidth difference sum;
and determining the bandwidth fluctuation rate of the first moment according to the bandwidth peak value, the maximum positive bandwidth differential value, the maximum negative bandwidth differential value and the bandwidth differential sum.
Optionally, the determining the bandwidth fluctuation value at the first time according to the bandwidth fluctuation gain at the first time and the bandwidth fluctuation value at the second time includes:
summing the bandwidth fluctuation gain at the first moment and the bandwidth fluctuation value at the second moment to obtain an original bandwidth fluctuation value at the first moment;
and normalizing the original bandwidth fluctuation value at the first moment to obtain the bandwidth fluctuation value at the first moment.
The bandwidth fluctuation value at the first moment is determined based on the existing bandwidth fluctuation value at the second moment, so that the calculated amount and the resource consumption are reduced, and the requirement of the production environment on the detection real-time property can be well met.
Optionally, the smoothing the bandwidth data of the resource device at the first time, and sending the smoothed bandwidth data at the first time to the scheduling system includes:
determining initial smooth bandwidth data of the first moment according to the bandwidth data of the first moment and the smoothed bandwidth data of the second moment;
and compensating the initial smooth bandwidth data at the first moment by adopting a bandwidth compensation value, and sending the compensated initial smooth bandwidth data at the first moment to a scheduling system.
The bandwidth compensation mode is adopted to carry out smoothing processing on the bandwidth data with large volatility, so that the problem of bandwidth distortion caused in the early stage of smoothing can be effectively avoided, and meanwhile, the smooth bandwidth data can be sent to the scheduling system, so that the scheduling system can accurately know the load condition of resource equipment, the accuracy of resource scheduling is improved, and the experience of customers is improved.
Optionally, the method further comprises:
and when the bandwidth fluctuation value at the first moment is determined not to be larger than the preset threshold value, sending the bandwidth data of the resource equipment at the first moment to a scheduling system.
Optionally, when the second time is an initial time of bandwidth smoothing, determining a bandwidth fluctuation value at the second time in the following manner:
acquiring bandwidth data of the resource equipment in a second time window corresponding to the second moment;
determining a bandwidth difference value and a bandwidth mean value in the second time window according to the bandwidth data in the second time window;
and determining the bandwidth fluctuation value at the second moment according to the bandwidth difference value and the bandwidth average value in the second time window.
The bandwidth difference value and the bandwidth mean value are determined according to the historical bandwidth data corresponding to the initial moment, and then the initial bandwidth fluctuation value is determined according to the bandwidth difference value and the bandwidth mean value, so that initial fluctuation value reference is provided for subsequent bandwidth fluctuation detection based on a sliding time window, and the accuracy of the subsequent bandwidth fluctuation detection is improved.
In one aspect, an embodiment of the present application provides a bandwidth smoothing device, including:
an obtaining module, configured to obtain bandwidth data of a resource device within a first time window, where the first time window is a time period determined based on a first time;
the processing module is used for determining the bandwidth fluctuation gain of the first moment according to the bandwidth data in the first time window;
the fluctuation detection module is used for determining a bandwidth fluctuation value of the first moment according to the bandwidth fluctuation gain of the first moment and a bandwidth fluctuation value of a second moment, wherein the second moment is a moment before the first moment;
and the smoothing module is used for smoothing the bandwidth data of the resource equipment at the first moment when the bandwidth fluctuation value at the first moment is determined to be greater than a preset threshold value, and sending the smoothed bandwidth data at the first moment to the scheduling system.
Optionally, the processing module is specifically configured to:
determining a bandwidth peak value in the first time window and a bandwidth differential value in the first time window according to the bandwidth data in the first time window;
determining the bandwidth fluctuation rate of the first moment according to the bandwidth peak value in the first time window and the bandwidth difference value in the first time window;
and determining the bandwidth fluctuation gain of the first moment according to the bandwidth fluctuation rate of the first moment.
Optionally, the bandwidth data in the first time window includes bandwidth values acquired at each acquisition time in the first time window;
the processing module is specifically configured to:
taking the maximum bandwidth value as a bandwidth peak value in the bandwidth values acquired at each acquisition time in the first time window;
and determining a first-order difference value of bandwidth values of adjacent acquisition moments in the first time window.
Optionally, the processing module is specifically configured to:
dividing the bandwidth difference value within the first time window into a positive bandwidth difference value and a negative bandwidth difference value;
determining a maximum positive bandwidth difference value from the positive bandwidth difference values;
after taking absolute values of the negative bandwidth difference values, determining a maximum negative bandwidth difference value from the negative bandwidth difference values;
summing the bandwidth difference values in the first time window to obtain a bandwidth difference sum;
and determining the bandwidth fluctuation rate of the first moment according to the bandwidth peak value, the maximum positive bandwidth differential value, the maximum negative bandwidth differential value and the bandwidth differential sum.
Optionally, the fluctuation detection module is specifically configured to:
summing the bandwidth fluctuation gain at the first moment and the bandwidth fluctuation value at the second moment to obtain an original bandwidth fluctuation value at the first moment;
and normalizing the original bandwidth fluctuation value at the first moment to obtain the bandwidth fluctuation value at the first moment.
Optionally, the smoothing module is specifically configured to:
determining initial smooth bandwidth data of the first moment according to the bandwidth data of the first moment and the smoothed bandwidth data of the second moment;
and compensating the initial smooth bandwidth data at the first moment by adopting a bandwidth compensation value, and sending the compensated initial smooth bandwidth data at the first moment to a scheduling system.
Optionally, the smoothing module is further configured to:
and when the bandwidth fluctuation value at the first moment is determined not to be larger than the preset threshold value, sending the bandwidth data of the resource equipment at the first moment to a scheduling system.
Optionally, the fluctuation detection module is further configured to:
when the second moment is the initial moment of bandwidth smoothing, acquiring bandwidth data of the resource equipment in a second time window corresponding to the second moment;
determining a bandwidth difference value and a bandwidth mean value in the second time window according to the bandwidth data in the second time window;
and determining the bandwidth fluctuation value at the second moment according to the bandwidth difference value and the bandwidth average value in the second time window.
In one aspect, an embodiment of the present application provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the bandwidth smoothing method when executing the program.
In one aspect, embodiments of the present application provide a computer-readable storage medium storing a computer program executable by a computer device, where the program is executed by the computer device, and causes the computer device to execute the steps of the bandwidth smoothing method.
In the embodiment of the application, since the mobility detection is performed on the bandwidth data at the first moment, when it is determined that the bandwidth fluctuation value at the first moment is greater than the preset threshold, the bandwidth data at the first moment is subjected to smoothing, instead of smoothing the bandwidth data at each moment, so that bandwidth delay caused by global smoothing is avoided, and meanwhile, the smooth bandwidth data can be sent to the scheduling system, so that the scheduling system can accurately know the load condition of the resource equipment, the accuracy of resource scheduling is improved, and the experience of a user is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required to be used in the description of the embodiments will be briefly introduced below, and it is apparent that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings may be obtained according to the drawings without inventive labor.
Fig. 1 is a schematic diagram of a system architecture according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a bandwidth smoothing method according to an embodiment of the present application;
fig. 3 is a schematic flowchart of a method for determining a bandwidth fluctuation gain according to an embodiment of the present application;
fig. 4 is a schematic flowchart of a bandwidth smoothing method according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a bandwidth smoothing device according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clearly apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
For convenience of understanding, terms referred to in the embodiments of the present invention are explained below.
CDN (Content Delivery Network): an intelligent virtual network built on the basis of the existing network is built, and users can obtain needed contents nearby by means of functional modules of load balancing, content distribution, scheduling and the like of a central platform by means of edge servers deployed in various places, so that network congestion is reduced, and access response speed and hit rate of the users are improved.
Referring to fig. 1, it is a system architecture diagram applicable to the embodiment of the present application, and the system architecture includes at least a resource device 101, a bandwidth smoothing device 102, a scheduling system 103, and a user terminal 104.
The resource device 101 is a user access point, is a content providing device facing an end user, and can cache static Web content and streaming media content, implement edge propagation and storage of the content, so that the user can access nearby, and the resource device 101 may be a node group consisting of one node or a plurality of nodes in the CDN network.
The bandwidth smoothing device 102 acquires bandwidth data of the resource device 101 in real time, and determines whether to smooth the bandwidth data of the resource device 101 based on the bandwidth data of the resource device 101, which includes the following specific steps: bandwidth data of a resource device within a first time window is first obtained, where the first time window is a period of time determined based on a first time. And then determining the bandwidth fluctuation gain at the first moment according to the bandwidth data in the first time window, and determining the bandwidth fluctuation value at the first moment according to the bandwidth fluctuation gain at the first moment and the bandwidth fluctuation value at the second moment, wherein the second moment is a moment before the first moment. And when the bandwidth fluctuation value at the first moment is determined to be larger than the preset threshold value, performing smoothing processing on the bandwidth data of the resource equipment at the first moment, and sending the smoothed bandwidth data at the first moment to the scheduling system, otherwise, directly sending the bandwidth data at the first moment to the scheduling system. The bandwidth smoothing device 102 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a network service, cloud communication, a middleware service, a domain name service, a security service, a CDN, and a big data and artificial intelligence platform. The bandwidth smoothing device 102 and the acquisition resource device 101 may be directly or indirectly connected through wired or wireless communication, which is not limited herein.
The scheduling system 103 is located at a user access centralized point, and is configured to balance loads of the multiple resource devices 101, thereby implementing load balancing and access control. In a specific implementation, the scheduling system 103 balances the load of each resource device 101 based on the bandwidth data sent by the bandwidth smoothing device 102, and schedules the user request of the user terminal 104 to the appropriate resource device 101. The scheduling system 103 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a network service, cloud communication, a middleware service, a domain name service, a security service, a CDN, a big data and artificial intelligence platform, and the like. The resource collecting device 101, the bandwidth smoothing device 102, and the scheduling system 103 may be directly or indirectly connected through wired or wireless communication, which is not limited herein.
The user terminal 104 has an application installed in advance, and the application may be a shopping application, a live application, a video application, an instant messaging application, or the like. For example, during a campaign promotion, a user inputs an operation related to purchasing goods in a shopping application, the shopping application responds to the user operation, sends a user request to the scheduling system 103 through the user terminal 104, and the scheduling system 103 selects a target resource device according to a load condition of each resource device 101, and then schedules the user request to the target resource device. The target resource device responds to the user request by sending response data to the user terminal 104. The user terminal 104 may be, but is not limited to, a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and the like.
Based on the system architecture diagram shown in fig. 1, the embodiment of the present application provides a flow of a bandwidth smoothing method, as shown in fig. 2, the flow of the method is executed by a bandwidth smoothing device, and includes the following steps:
step S201, obtaining bandwidth data of the resource device in the first time window.
Specifically, the acquisition program in the resource device acquires bandwidth data from the switch/machine of the periodic production environment and sends the bandwidth data to the bandwidth smoothing device, and the bandwidth smoothing device collects and backs up the bandwidth data. Because the original bandwidth data need to be cleaned due to the reasons of acquisition problems or machine abnormality and the like, the abnormal bandwidth data, such as negative values, are removed in a filtering mode in the application. In order not to affect the analysis of the subsequent bandwidth fluctuation, after the abnormal bandwidth data is removed, linear interpolation (or other interpolation algorithms) is adopted to supplement the bandwidth data.
In this application, the first time may be a real time point, for example, 10. The first time window is a time period determined based on the first time, the duration of the time period is preset, and the durations of different time windows can be set to be the same value or different values.
Exemplarily, setting the first time to 10, and presetting the duration of the first time window to 10 minutes, the time period corresponding to the first time window is 9.
Step S202, according to the bandwidth data in the first time window, determining the bandwidth fluctuation gain at the first time.
Specifically, the bandwidth data in the first time window is the bandwidth data that the resource device sends to the bandwidth smoothing device in the first time window. For example, the time period corresponding to the first time window is 9 to 10, and then the bandwidth data in the first time window is framed data that is acquired by the resource device at 9.
And step S203, determining the bandwidth fluctuation value at the first moment according to the bandwidth fluctuation gain at the first moment and the bandwidth fluctuation value at the second moment.
Specifically, the second time is a time before the first time, a time interval between the first time and the second time is preset according to timeliness of bandwidth smoothing, and a bandwidth fluctuation value of the second time is determined according to bandwidth data in a second time window corresponding to the second time. For example, the first time is 10.
And step S204, when the bandwidth fluctuation value at the first moment is determined to be larger than the preset threshold value, performing smoothing processing on the bandwidth data of the resource equipment at the first moment, and sending the smoothed bandwidth data at the first moment to the scheduling system.
Specifically, when the bandwidth fluctuation value at the first time is greater than the preset threshold, it is indicated that the bandwidth at the first time is unstable, and if the bandwidth data is directly sent to the scheduling system, the scheduling system cannot accurately grasp the load condition of the resource device, so that the scheduling is inaccurate.
And when the bandwidth fluctuation value at the first moment is determined not to be larger than the preset threshold value, sending the bandwidth data of the resource equipment at the first moment to a scheduling system. In specific implementation, when the bandwidth fluctuation value at the first moment is not greater than the preset threshold, it is indicated that the bandwidth at the first moment is stable, so that the bandwidth data can be directly sent to the scheduling system.
In the embodiment of the application, since the mobility detection is performed on the bandwidth data at the first moment, when it is determined that the bandwidth fluctuation value at the first moment is greater than the preset threshold, the bandwidth data at the first moment is subjected to smoothing, instead of smoothing the bandwidth data at each moment, so that bandwidth delay caused by global smoothing is avoided, and meanwhile, the smooth bandwidth data can be sent to the scheduling system, so that the scheduling system can accurately know the load condition of the resource equipment, the accuracy of resource scheduling is improved, and the experience of a user is improved.
Alternatively, in the step S203, when the second time is the initial time of bandwidth smoothing, the bandwidth fluctuation value at the second time is determined in the following manner:
the method comprises the steps of firstly obtaining bandwidth data of resource equipment in a second time window corresponding to a second time, then determining a bandwidth difference value and a bandwidth mean value in the second time window according to the bandwidth data in the second time window, and then determining a bandwidth fluctuation value at the second time according to the bandwidth difference value and the bandwidth mean value in the second time window.
Specifically, the bandwidth difference value may be a first order difference value, a second order difference value, or the like. For example, the bandwidth difference value is used as a first-order difference value, and the bandwidth difference value in the second time window is determined according to the bandwidth data in the second time window, which specifically satisfies the following formula (1):
Diff2＝Bwi2 t -Bwi2 t-1 ……………(1)
wherein Diff2 is a first order difference value in the second time window, bwi2 t Is the bandwidth value of the t-th time in the second time window, bwi2 t-1 In an implementation, the bandwidth value at the tth time point in the second time window may be the bandwidth value at the second time point, which is the bandwidth value at the T-1 time point in the second time window, T ∈ (2, 3, \8230;, T).
Determining a bandwidth average value in the second time window according to the bandwidth data in the second time window, wherein the following formula (2) is specifically satisfied:
wherein BwiMean is the bandwidth average in the second time window.
Further, a bandwidth standard deviation σ (Diff) or a bandwidth variance σ (Diff) in the second time window may be determined based on the bandwidth difference values in the second time window 2 And then determining the bandwidth fluctuation value at the second moment according to the bandwidth standard deviation or the bandwidth variance and the bandwidth mean value in the second time window.
Specifically, the bandwidth fluctuation value at the second time is determined according to the bandwidth standard deviation and the bandwidth mean value in the second time window, and the following formula (3) is specifically satisfied:
wherein, bwiMean is the bandwidth average value in the second time window, σ (Diff) is the bandwidth standard deviation in the second time window, and WaveCoe is the bandwidth fluctuation value at the second time.
And determining a bandwidth fluctuation value at the second moment according to the bandwidth standard deviation and the bandwidth mean value in the second time window, wherein the following formula (4) is specifically satisfied:
wherein Bwimean is the bandwidth mean, σ (Diff) in the second time window 2 The WaveCoe is a bandwidth fluctuation value at the second time.
Further, an AnormalyPoint array is preset to store a bandwidth fluctuation value, and after an initial bandwidth fluctuation value is obtained, a first value AnormalyPoint in the AnormalyPoint array is set 0 An initial bandwidth fluctuation value is set.
In the embodiment of the application, the bandwidth difference value and the bandwidth mean value are determined according to the historical bandwidth data corresponding to the initial time, and then the initial bandwidth fluctuation value is determined according to the bandwidth difference value and the bandwidth mean value, so that the initial fluctuation value reference is provided for the subsequent bandwidth fluctuation detection based on the sliding time window, and the accuracy of the subsequent bandwidth fluctuation detection is improved.
Optionally, in the step S202, the following manner is adopted to determine the bandwidth fluctuation gain at the first time, as shown in fig. 3, and the method specifically includes the following steps:
step S301, according to the bandwidth data in the first time window, determining a bandwidth peak value in the first time window and a bandwidth differential value in the first time window.
The bandwidth data in the first time window includes bandwidth values acquired at respective acquisition times in the first time window, and the bandwidth difference value may be a first order difference value, a second order difference value, or the like.
In a specific implementation, the maximum bandwidth value among the bandwidth values acquired at each acquisition time within the first time window is taken as a bandwidth peak value.
Determining a first order difference value of bandwidth values of adjacent acquisition times within the first time window using the following equation (5):
Diff1＝Bwi1 t -Bwi1 t-1 ……………(5)
wherein Diff1 is a first order difference value in the first time window, bwi1 t Is the bandwidth value of the t-th time in the first time window, bwi1 t-1 In an implementation, the bandwidth value at the T-1 th time within the first time window, T ∈ (2, 3, \8230;, T), may be the bandwidth value at the first time.
Step S302, determining the bandwidth fluctuation rate at the first time according to the bandwidth peak value in the first time window and the bandwidth difference value in the first time window.
Specifically, the bandwidth difference values in the first time window are divided into positive bandwidth difference values and negative bandwidth difference values, then the maximum positive bandwidth difference value is determined from each positive bandwidth difference value, and after the absolute value of each negative bandwidth difference value is taken, the maximum negative bandwidth difference value is determined from each negative bandwidth difference value. And summing the bandwidth difference values in the first time window to obtain a bandwidth difference sum, and then determining the bandwidth fluctuation rate at the first moment according to the bandwidth peak value, the maximum positive bandwidth difference value, the maximum negative bandwidth difference value and the bandwidth difference sum.
In specific implementation, the positive differential value set diff is preset positive And negative differential value set diff negative After calculating the bandwidth difference value in the first time window, dividing the positive bandwidth difference value into a positive difference value set diff positive Dividing the negative bandwidth difference value into a negative difference value set diff negative 。
The maximum positive bandwidth difference value is determined using the following equation (6):
diff posmax ＝max(diff positive )……………(6)
wherein, diff posmax Is the maximum positive bandwidth difference value.
Determining a maximum negative bandwidth difference value using the following equation (7):
diff negmax ＝max(abs(diff negative ))……………(7)
wherein, diff negmax Is the maximum negative bandwidth difference value.
Then, the bandwidth fluctuation rate at the first time is determined by the following formula (8):
wherein, anormalyRate is the bandwidth fluctuation rate at the first moment, bwi peak Is the bandwidth peak value in the first time window, alpha is the bandwidth peak value control coefficient, diff sum For the bandwidth differential sum in the first time window, the bandwidth differential sum may be obtained by directly summing the bandwidth differential values in the first time window, or by summing the absolute values of the bandwidth differential values in the first time window.
Step S303, determining the bandwidth fluctuation gain at the first time according to the bandwidth fluctuation rate at the first time.
Specifically, the following equation (9) is used to obtain the bandwidth fluctuation gain at the first time.
Wherein, anormalyGain is the bandwidth fluctuation gain at the first moment, anormalyRate is the bandwidth fluctuation rate at the first moment, β is the proportional control coefficient when the bandwidth is stable, and γ is the proportional control coefficient when the bandwidth fluctuates.
In the embodiment of the application, the bandwidth peak value and the bandwidth difference value are adopted to determine the bandwidth fluctuation rate, and then the bandwidth fluctuation gain is determined based on the bandwidth fluctuation rate, so that the bandwidth peak value and the bandwidth fluctuation are considered, the fluctuation condition of the bandwidth of a node/group under the normal condition can be identified, the sudden increase/sudden decrease condition concerned by a scheduling system can be judged, and the problem of misadjustment or misadjustment caused by the loss of sudden increase/sudden decrease information is avoided.
Optionally, in step S203, the present application provides at least the following two implementation manners to obtain the bandwidth fluctuation value at the first time:
in one possible implementation, the bandwidth fluctuation gain at the first time and the bandwidth fluctuation value at the second time are summed to obtain an original bandwidth fluctuation value at the first time, and then the original bandwidth fluctuation value at the first time is normalized to obtain a bandwidth fluctuation value at the first time.
In a specific implementation, when the second time is the initial time, the bandwidth fluctuation value at the second time is determined by using the above-described formula (1) to formula (3). When the second time is not the initial time, determining a bandwidth fluctuation value of the second time based on the bandwidth fluctuation gain of the second time and a bandwidth fluctuation value of a third time, the third time being a time before the second time.
Summing the bandwidth fluctuation gain at the first moment and the bandwidth fluctuation value at the second moment to obtain an original bandwidth fluctuation value at the first moment, wherein the original bandwidth fluctuation value at the first moment specifically satisfies the following formula (10):
CurAnormaly＝AnormalyPoing i-1 +AnormalyGain………(10)
wherein, anarmalygain is the bandwidth fluctuation gain of the first moment, anarmalyPoing i-1 The bandwidth fluctuation value at the second time is the i-1 th time for performing bandwidth smoothing, and curunormaly is the original bandwidth fluctuation value at the first time.
Normalizing the original bandwidth fluctuation value at the first moment to obtain the bandwidth fluctuation value at the first moment, wherein the following formula (11) is specifically satisfied:
wherein, anormalyPoint i For the bandwidth fluctuation value at the first time, curannormaly is the original bandwidth fluctuation value at the first time, and the first time is the ith time for performing bandwidth smoothing.
In one possible implementation, the bandwidth fluctuation gain at the first time and the bandwidth fluctuation value at the second time are summed to obtain the bandwidth fluctuation value at the first time.
In a specific implementation, the sum of the bandwidth fluctuation gain at the first time and the bandwidth fluctuation value at the second time can be directly used as the bandwidth fluctuation value at the first time.
In the embodiment of the application, the bandwidth fluctuation value at the first moment is determined based on the existing bandwidth fluctuation value at the second moment, so that the calculated amount and the resource consumption are reduced, and the requirement of a production environment on detection real-time property can be well met.
Optionally, in step S204, this embodiment of the present application provides at least the following two implementation manners, to perform smoothing processing on bandwidth data of the resource device at the first time:
in one possible implementation, the initial smoothed bandwidth data at the first time is determined according to the bandwidth data at the first time and the bandwidth data at the second time after the smoothing process, and the following formula (12) is specifically satisfied:
Bwi1’ i ＝βSmoothBwi2 i-1 +(1-β)CurBwi1 i ………(12)
wherein, bwi1' i Is the initial smoothing bandwidth data of the first time, the first time is the ith time for performing bandwidth smoothing, smoothBwi2 i-1 The second time is the i-1 time for performing bandwidth smoothing, curBwi1 i The data of the bandwidth at the first moment is beta, and the beta is a proportional control coefficient when the bandwidth is stable.
Compensating the initial smooth bandwidth data at the first moment by using a bandwidth compensation value, sending the compensated bandwidth data at the first moment to a scheduling system, and compensating the initial smooth bandwidth data at the first moment to specifically satisfy the following formula (13):
wherein, the first time is the ith time for performing bandwidth smoothing, smoothBwi1 i For the compensated bandwidth data at the first time instant,
for a predetermined compensation factor, bwi1’ i The initial smoothed bandwidth data for the first time instant.
In one possible implementation, the bandwidth compensation value is used to compensate the bandwidth data at the first time, and the compensated bandwidth data at the first time is sent to the scheduling system.
In specific implementation, when it is detected that a bandwidth fluctuation value at a first time is greater than a preset threshold, performing direct smoothing compensation on bandwidth data of a resource device at the first time to obtain smoothed bandwidth data, and then sending the smoothed bandwidth data to a scheduling system, specifically performing smoothing compensation on the bandwidth data of the resource device at the first time by using the following formula (14):
wherein the first time is the ith time for performing bandwidth smoothing, smoothBwi1 i For the compensated bandwidth data at the first time instant,
for a predetermined compensation factor, curBwi1 i Is the bandwidth data of the first time.
In the embodiment of the application, the bandwidth data with high volatility is smoothed in a bandwidth compensation mode, so that the problem of bandwidth distortion caused by the smoothing initial stage can be effectively avoided, and meanwhile, the smoothed bandwidth data can be sent to the scheduling system, so that the scheduling system can accurately know the load condition of the resource equipment, the accuracy of resource scheduling is improved, and the experience of customers is improved.
Further, when the bandwidth data is sent to the scheduling system, taking a preset threshold δ as a determination condition, when the bandwidth fluctuation value at the first time is greater than the preset threshold, performing smoothing processing on the bandwidth data of the resource device at the first time, and sending the bandwidth data at the first time after the smoothing processing to the scheduling system. When the bandwidth fluctuation value at the first moment is not greater than the preset threshold, directly sending the bandwidth data at the first moment to a scheduling system, wherein the following formula (15) is specifically satisfied:
wherein, smoothBwi1 i CorrectBo for the compensated first time-instant bandwidth data i CurBwi1, bandwidth data for a first time instant sent by a bandwidth smoothing device to a scheduling system i Is the bandwidth data of the first time.
The method comprises the steps of firstly carrying out mobility detection on the bandwidth data at the first moment, carrying out smoothing processing on the bandwidth data at the first moment when the bandwidth fluctuation value at the first moment is determined to be larger than a preset threshold value, and sending the smoothed bandwidth data to a scheduling system, otherwise, directly sending the bandwidth data at the first moment to the scheduling system instead of carrying out smoothing processing on the bandwidth data at each moment, so that bandwidth delay caused by global smoothing is avoided, and meanwhile, the smoothed bandwidth data can be sent to the scheduling system, so that the scheduling system can accurately acquire the load condition of resource equipment, the accuracy of resource scheduling is improved, and the user experience is improved.
In order to better explain the embodiments of the present application, a bandwidth smoothing method provided by the embodiments of the present application is described in stages below, and the method is executed by a bandwidth smoothing device, and as shown in fig. 4, the method includes three stages, which are a data processing stage, a volatility detection stage, and a data output stage.
The data preprocessing stage comprises data acquisition, data cleaning and data preprocessing.
The data acquisition specifically comprises the following steps: the acquisition program in the resource device acquires bandwidth data from the switch/machine of the periodic production environment and sends the bandwidth data to the bandwidth smoothing device, and the bandwidth smoothing device collects and backs up the bandwidth data.
The data cleaning specifically comprises the following steps: and removing abnormal bandwidth data by adopting a filtering mode, such as removing negative values.
The data preprocessing specifically comprises the following steps: after removing the abnormal bandwidth data, linear interpolation (or other interpolation algorithm) is adopted to supplement the bandwidth data.
The volatility detection stage comprises initial volatility detection and real-time volatility detection.
The initial fluctuation detection specifically comprises the following steps: setting the time 1 as an initial time of bandwidth smoothing, firstly acquiring bandwidth data of the resource device in a time window 1 corresponding to the time 1, then determining a bandwidth difference value and a bandwidth mean value in the time window 1 according to the bandwidth data in the time window 1, and then determining a bandwidth fluctuation value at the time 1 according to the bandwidth difference value and the bandwidth mean value in the time window 1.
The real-time fluctuation detection specifically comprises the following steps: acquiring bandwidth data of the resource device in a time window N, wherein the time window N is a time period determined based on the time N, and the bandwidth data in the time window N comprises bandwidth values acquired at each acquisition time in the time window N. And calculating a first-order difference value of bandwidth values of adjacent acquisition moments in the time window N by taking the maximum bandwidth value as a bandwidth peak in the bandwidth values acquired at the acquisition moments in the time window N. Then dividing the bandwidth difference value in the time window N into a positive bandwidth difference value and a negative bandwidth difference value, determining the maximum positive bandwidth difference value from the positive bandwidth difference values, taking the absolute value of each negative bandwidth difference value, determining the maximum negative bandwidth difference value from the negative bandwidth difference values, and summing the bandwidth difference values in the time window N to obtain the bandwidth difference sum. And determining the bandwidth fluctuation rate of the moment N according to the bandwidth peak value, the maximum positive bandwidth difference value, the maximum negative bandwidth difference value, the bandwidth difference sum.
And determining the bandwidth fluctuation gain of the moment N according to the bandwidth fluctuation rate of the moment N. And summing the bandwidth fluctuation gain at the moment N and the bandwidth fluctuation value at the moment N-1 to obtain an original bandwidth fluctuation value at the moment N, and then carrying out normalization processing on the original bandwidth fluctuation value at the moment N to obtain the bandwidth fluctuation value at the moment N.
And a data output stage: taking a preset threshold value delta as a judgment condition, when the bandwidth fluctuation value at the moment N is greater than the preset threshold value delta, performing smoothing processing on the bandwidth data of the resource equipment at the moment N, and sending the bandwidth data at the moment N after the smoothing processing to a scheduling system, wherein the smoothing processing specifically comprises the following steps: and determining initial smooth bandwidth data of the time N according to the bandwidth data of the time N and the bandwidth data of the smoothed time N-1. And compensating the initial smooth bandwidth data at the time N by adopting a bandwidth compensation value to obtain the bandwidth data at the time N after the smoothing treatment. And when the bandwidth fluctuation value at the moment N is not greater than a preset threshold value delta, directly sending the bandwidth data at the moment N to a scheduling system.
In the embodiment of the application, since the mobility detection is performed on the bandwidth data at the first moment, when it is determined that the bandwidth fluctuation value at the first moment is greater than the preset threshold, the bandwidth data at the first moment is subjected to smoothing, instead of smoothing the bandwidth data at each moment, so that bandwidth delay caused by global smoothing is avoided, and meanwhile, the smooth bandwidth data can be sent to the scheduling system, so that the scheduling system can accurately know the load condition of the resource equipment, the accuracy of resource scheduling is improved, and the experience of a user is improved.
Based on the same technical concept, the embodiment of the present application provides a bandwidth smoothing device, as shown in fig. 5, the device 500 includes:
an obtaining module 501, configured to obtain bandwidth data of a resource device in a first time window, where the first time window is a time period determined based on a first time;
a processing module 502, configured to determine a bandwidth fluctuation gain at a first time according to bandwidth data in a first time window;
the fluctuation detection module 503 is configured to determine a bandwidth fluctuation value at a first time according to the bandwidth fluctuation gain at the first time and a bandwidth fluctuation value at a second time, where the second time is a time before the first time;
the smoothing module 504 is configured to, when it is determined that the bandwidth fluctuation value at the first time is greater than the preset threshold, perform smoothing processing on the bandwidth data of the resource device at the first time, and send the bandwidth data at the first time after the smoothing processing to the scheduling system.
Optionally, the processing module 502 is specifically configured to:
determining a bandwidth peak value in the first time window and a bandwidth differential value in the first time window according to the bandwidth data in the first time window;
determining the bandwidth fluctuation rate at a first moment according to the bandwidth peak value in the first time window and the bandwidth difference value in the first time window;
and determining the bandwidth fluctuation gain of the first moment according to the bandwidth fluctuation rate of the first moment.
Optionally, the bandwidth data in the first time window includes bandwidth values acquired at each acquisition time in the first time window;
the processing module 502 is specifically configured to:
taking the maximum bandwidth value as a bandwidth peak value in the bandwidth values acquired at each acquisition time in the first time window;
and determining a first-order difference value of bandwidth values of adjacent acquisition moments in the first time window.
Optionally, the processing module 502 is specifically configured to:
dividing the bandwidth difference value in the first time window into a positive bandwidth difference value and a negative bandwidth difference value;
determining a maximum positive bandwidth difference value from each positive bandwidth difference value;
determining the maximum negative bandwidth difference value from each negative bandwidth difference value after taking the absolute value of each negative bandwidth difference value;
summing the bandwidth difference values in the first time window to obtain a bandwidth difference sum;
and determining the bandwidth fluctuation rate at the first moment according to the bandwidth peak value, the maximum positive bandwidth differential value, the maximum negative bandwidth differential value and the bandwidth differential sum.
Optionally, the fluctuation detecting module 503 is specifically configured to:
summing the bandwidth fluctuation gain at the first moment and the bandwidth fluctuation value at the second moment to obtain an original bandwidth fluctuation value at the first moment;
and normalizing the original bandwidth fluctuation value at the first moment to obtain the bandwidth fluctuation value at the first moment.
Optionally, the smoothing module 504 is specifically configured to:
determining initial smooth bandwidth data at a first moment according to the bandwidth data at the first moment and the bandwidth data at a second moment after smoothing;
and compensating the initial smooth bandwidth data at the first moment by adopting a bandwidth compensation value, and sending the compensated initial smooth bandwidth data at the first moment to a scheduling system.
Optionally, the smoothing module 504 is further configured to:
and when the bandwidth fluctuation value at the first moment is determined not to be larger than the preset threshold value, sending the bandwidth data of the resource equipment at the first moment to a scheduling system.
Optionally, the fluctuation detection module 503 is further configured to:
when the second moment is the initial moment of bandwidth smoothing, acquiring bandwidth data of the resource equipment in a second time window corresponding to the second moment;
determining a bandwidth difference value and a bandwidth mean value in a second time window according to bandwidth data in the second time window;
and determining the bandwidth fluctuation value at the second moment according to the bandwidth difference value and the bandwidth mean value in the second time window.
Based on the same technical concept, the embodiment of the present application provides a computer device, as shown in fig. 6, including at least one processor 601 and a memory 602 connected to the at least one processor, where a specific connection medium between the processor 601 and the memory 602 is not limited in this embodiment, and a bus connection between the processor 601 and the memory 602 in fig. 6 is taken as an example. The bus may be divided into an address bus, a data bus, a control bus, etc.
In the embodiment of the present application, the memory 602 stores instructions executable by the at least one processor 601, and the at least one processor 601 may execute the steps included in the foregoing bandwidth smoothing method by executing the instructions stored in the memory 602.
The processor 601 is a control center of the computer device, and can connect various parts of the computer device by using various interfaces and lines, and perform bandwidth smoothing by executing or executing instructions stored in the memory 602 and calling data stored in the memory 602. Alternatively, the processor 601 may include one or more processing units, and the processor 601 may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, an application program, and the like, and the modem processor mainly processes wireless communication. It will be appreciated that the modem processor described above may not be integrated into the processor 601. In some embodiments, processor 601 and memory 602 may be implemented on the same chip, or in some embodiments, they may be implemented separately on separate chips.
The processor 601 may be a general-purpose processor, such as a Central Processing Unit (CPU), a digital signal processor, an Application Specific Integrated Circuit (ASIC), a field programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof, configured to implement or perform the methods, steps, and logic blocks disclosed in the embodiments of the present Application. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware processor, or may be implemented by a combination of hardware and software modules in a processor.
The memory 602, which is a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. The Memory 602 may include at least one type of storage medium, and may include, for example, a flash Memory, a hard disk, a multimedia card, a card-type Memory, a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Programmable Read Only Memory (PROM), a Read Only Memory (ROM), a charge Erasable Programmable Read Only Memory (EEPROM), a magnetic Memory, a magnetic disk, an optical disk, and so on. The memory 602 is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to such. The memory 602 in the embodiments of the present application may also be circuitry or any other device capable of performing a storage function for storing program instructions and/or data.
Based on the same inventive concept, embodiments of the present application provide a computer-readable storage medium storing a computer program executable by a computer device, which, when the program is run on the computer device, causes the computer device to perform the steps of the above bandwidth smoothing method.
It should be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention has been described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (11)
1. A method of bandwidth smoothing, comprising:
acquiring bandwidth data of resource equipment in a first time window, wherein the first time window is a time period determined based on a first time;
determining the bandwidth fluctuation gain of the first moment according to the bandwidth data in the first time window;
determining a bandwidth fluctuation value of the first moment according to the bandwidth fluctuation gain of the first moment and a bandwidth fluctuation value of a second moment, wherein the second moment is a moment before the first moment;
and when the bandwidth fluctuation value at the first moment is determined to be larger than a preset threshold value, performing smoothing processing on the bandwidth data of the resource equipment at the first moment, and sending the smoothed bandwidth data at the first moment to a scheduling system.
2. The method of claim 1, wherein determining the bandwidth fluctuation gain for the first time instant based on the bandwidth data within the first time window comprises:
determining a bandwidth peak value in the first time window and a bandwidth differential value in the first time window according to the bandwidth data in the first time window;
determining the bandwidth fluctuation rate of the first moment according to the bandwidth peak value in the first time window and the bandwidth difference value in the first time window;
and determining the bandwidth fluctuation gain of the first moment according to the bandwidth fluctuation rate of the first moment.
3. The method of claim 2, wherein the bandwidth data within the first time window comprises bandwidth values acquired at respective acquisition instants within the first time window;
determining a bandwidth peak value in the first time window and a bandwidth differential value in the first time window according to the bandwidth data in the first time window, including:
taking the maximum bandwidth value of the bandwidth values acquired at each acquisition time in the first time window as a bandwidth peak value;
and determining a first-order difference value of bandwidth values of adjacent acquisition moments in the first time window.
4. The method of claim 2, wherein determining the bandwidth fluctuation rate for the first time instant as a function of the bandwidth peak within the first time window and the bandwidth difference value within the first time window comprises:
dividing the bandwidth difference value within the first time window into a positive bandwidth difference value and a negative bandwidth difference value;
determining a maximum positive bandwidth difference value from the positive bandwidth difference values;
determining the maximum negative bandwidth difference value from each negative bandwidth difference value after taking the absolute value of each negative bandwidth difference value;
summing the bandwidth difference values in the first time window to obtain a bandwidth difference sum;
and determining the bandwidth fluctuation rate of the first moment according to the bandwidth peak value, the maximum positive bandwidth differential value, the maximum negative bandwidth differential value and the bandwidth differential sum.
5. The method as claimed in claim 1, wherein said determining the bandwidth fluctuation value of the first time instant according to the bandwidth fluctuation gain of the first time instant and the bandwidth fluctuation value of the second time instant comprises:
summing the bandwidth fluctuation gain at the first moment and the bandwidth fluctuation value at the second moment to obtain an original bandwidth fluctuation value at the first moment;
and normalizing the original bandwidth fluctuation value at the first moment to obtain the bandwidth fluctuation value at the first moment.
6. The method of claim 1, wherein smoothing the bandwidth data of the resource device at a first time and sending the smoothed bandwidth data at the first time to a scheduling system comprises:
determining initial smooth bandwidth data of the first moment according to the bandwidth data of the first moment and the smoothed bandwidth data of the second moment;
and compensating the initial smooth bandwidth data at the first moment by adopting a bandwidth compensation value, and sending the compensated initial smooth bandwidth data at the first moment to a scheduling system.
7. The method of any of claims 1 to 6, further comprising:
and when the bandwidth fluctuation value at the first moment is determined not to be larger than the preset threshold value, sending the bandwidth data of the resource equipment at the first moment to a scheduling system.
8. The method of claim 7, wherein when the second time is an initial time of bandwidth smoothing, determining the bandwidth fluctuation value of the second time in the following manner:
acquiring bandwidth data of the resource equipment in a second time window corresponding to the second moment;
determining a bandwidth difference value and a bandwidth mean value in the second time window according to the bandwidth data in the second time window;
and determining the bandwidth fluctuation value at the second moment according to the bandwidth difference value and the bandwidth average value in the second time window.
9. A bandwidth smoothing device, comprising:
an obtaining module, configured to obtain bandwidth data of a resource device within a first time window, where the first time window is a time period determined based on a first time;
the processing module is used for determining the bandwidth fluctuation gain at the first moment according to the bandwidth data in the first time window;
the fluctuation detection module is used for determining a bandwidth fluctuation value of the first moment according to the bandwidth fluctuation gain of the first moment and a bandwidth fluctuation value of a second moment, wherein the second moment is a moment before the first moment;
and the smoothing module is used for smoothing the bandwidth data of the resource equipment at the first moment when the bandwidth fluctuation value at the first moment is determined to be larger than a preset threshold value, and sending the smoothed bandwidth data at the first moment to a scheduling system.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the steps of the method of any one of claims 1 to 8 are performed when the program is executed by the processor.
11. A computer-readable storage medium, in which a computer program is stored which is executable by a computer device, and which, when run on the computer device, causes the computer device to carry out the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010921218.6A CN112187870B (en) | 2020-09-04 | 2020-09-04 | Bandwidth smoothing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010921218.6A CN112187870B (en) | 2020-09-04 | 2020-09-04 | Bandwidth smoothing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112187870A CN112187870A (en) | 2021-01-05 |
| CN112187870B true CN112187870B (en) | 2022-10-11 |
Family
ID=73924810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010921218.6A Active CN112187870B (en) | 2020-09-04 | 2020-09-04 | Bandwidth smoothing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112187870B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115022212B (en) * | 2022-06-01 | 2024-04-16 | 海光信息技术股份有限公司 | Bandwidth monitoring method, device, circuit and electronic equipment |
| CN115659134B (en) * | 2022-11-02 | 2024-03-22 | 上海米硅科技有限公司 | Signal processing method for improving sensitivity of chip and related device |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| IL143540A0 (en) * | 2000-06-09 | 2002-04-21 | Hughes Electronics Corp | Available bandwidth control mechanism |
| CN103368811B (en) * | 2012-04-06 | 2016-08-10 | 华为终端有限公司 | Bandwidth allocation methods and equipment |
| CN103746934A (en) * | 2013-12-24 | 2014-04-23 | 乐视网信息技术（北京）股份有限公司 | CDN bandwidth balancing method, CDN control center and system |
| CN105376805B (en) * | 2015-11-24 | 2018-06-08 | 上海师范大学 | One kind is based on the prediction adjustable heterogeneous wireless network load-balancing method of service bandwidth |
| CN106059954B (en) * | 2016-05-27 | 2019-08-02 | 青岛海信电器股份有限公司 | A kind of method and device that network bandwidth is adjusted |
| CN107770145A (en) * | 2016-08-23 | 2018-03-06 | 中兴通讯股份有限公司 | A kind of method and apparatus of Bandwidth Management |
| CN109039833B (en) * | 2018-09-30 | 2022-11-22 | 网宿科技股份有限公司 | Method and device for monitoring bandwidth state |
| CN110807024B (en) * | 2019-10-12 | 2022-04-19 | 广州市申迪计算机系统有限公司 | Dynamic threshold anomaly detection method and system, storage medium and intelligent device |
| CN110890998B (en) * | 2019-11-06 | 2021-08-27 | 厦门网宿有限公司 | Method and device for determining threshold |
| CN111082884B (en) * | 2019-12-16 | 2022-03-04 | 京信网络系统股份有限公司 | Broadband fluctuation calibration method and device and repeater system |
-
2020
- 2020-09-04 CN CN202010921218.6A patent/CN112187870B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112187870A (en) | 2021-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104951465B (en) | Application recommendation method and device | |
| CN112187870B (en) | Bandwidth smoothing method and device | |
| EP4198775A1 (en) | Abnormal user auditing method and apparatus, electronic device, and storage medium | |
| CN114500339B (en) | Node bandwidth monitoring method and device, electronic equipment and storage medium | |
| CN108595448B (en) | Information pushing method and device | |
| CN115134368B (en) | Load balancing method, device, equipment and storage medium | |
| CN112734494A (en) | Sales prediction method and device, terminal equipment and readable storage medium | |
| WO2023029680A1 (en) | Method and apparatus for determining usable duration of magnetic disk | |
| CN112506619A (en) | Job processing method, apparatus, electronic device, storage medium, and program product | |
| US20140351414A1 (en) | Systems And Methods For Providing Prediction-Based Dynamic Monitoring | |
| CN115291503A (en) | Recommendation method, recommendation device, electronic device and storage medium | |
| US20190392312A1 (en) | Method for quantizing a histogram of an image, method for training a neural network and neural network training system | |
| CN111143070A (en) | Resource scheduling method and device | |
| CN110971435A (en) | Alarm method and device | |
| WO2023087705A1 (en) | Resource prediction method and apparatus | |
| CN114553614B (en) | Bandwidth cost estimation method, device, equipment, medium and program product | |
| CN116192752A (en) | Service flow control method, device, electronic equipment and storage medium | |
| CN110969481A (en) | Product data prediction method, device, computer equipment and storage medium | |
| CN116382892A (en) | Load balancing method and device based on multi-cloud fusion and cloud service | |
| US11593014B2 (en) | System and method for approximating replication completion time | |
| CN115129964A (en) | Method for pushing content item to be recommended, pushing system and electronic equipment | |
| CN115312208B (en) | Method, device, equipment and medium for displaying treatment data | |
| CN112994978B (en) | Network traffic monitoring method and device | |
| CN111339156B (en) | Method, apparatus and computer readable storage medium for long-term determination of business data | |
| RU2809340C1 (en) | Method, device and electronic device for recommending video and data carrier |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |